CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-slides

Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, actionable multi-phase workflow with strong validation and checkpointing. Its main weaknesses are redundant rule repetition between Phase 2 and Key Rules, and bulky inlined templates that would benefit from being split into reference files.

Suggestions

Remove the 'Key Rules' section's duplication of Phase 2 rules (one-message-per-slide, font minimums, progressive disclosure, no-fabrication) — keep each rule in one place and cross-reference if needed.

Extract the full beamer LaTeX template and the talk-script/Q&A template into separate reference files (e.g., references/beamer_template.tex, references/talk_script_template.md) and link to them from SKILL.md to improve progressive disclosure.

Replace the placeholder Codex review pseudocode with a concrete, copy-paste-ready invocation (or explicitly justify the placeholder) so the review phase is fully executable.

DimensionReasoningScore

Conciseness

Mostly efficient and earns its length via executable templates, but the 'Key Rules' section repeats Phase 2 rules verbatim (one-message-per-slide, font minimums, progressive disclosure, fabrication/hallucination warnings) and some templates could be tightened.

3 / 5

Actionability

Provides copy-paste-ready bash commands and a complete beamer LaTeX template with concrete checkpoints, but the PPTX generator is described rather than scripted verbatim and the Codex review block uses placeholder pseudocode.

4 / 5

Workflow Clarity

Eight clearly sequenced phases with explicit STOP checkpoints, per-phase state persistence, prerequisite checks, a backup step for the destructive overwrite, and a compile error-handling feedback loop (max 3 attempts) with page-count verification.

5 / 5

Progressive Disclosure

Good section structure (phases, tables), but large blocks that could live in separate reference files — the ~70-line beamer template and ~90-line talk-script/Q&A template — are fully inlined, and no bundle files ship alongside the skill.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states what it produces and gives an explicit, bilingual 'Use when' trigger list. It is comprehensive, distinct, and free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and outputs — 'beamer LaTeX → PDF + editable PPTX', 'speaker notes and full talk script' — giving comprehensive coverage of what the skill produces.

5 / 5

Completeness

Explicitly answers both 'what' (generate slides as PDF + PPTX with notes and script) and 'when' (a concrete 'Use when user says...' clause listing trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage across two languages — 'make slides', 'conference talk', 'presentation slides', '做PPT', '做幻灯片', '生成slides', '写演讲稿', 'beamer slides' — including synonyms and bilingual variants users would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — conference talk slides from a compiled paper — with triggers distinct from sibling skills like posters; minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (572 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.